Jie XU徐 杰Ph.D. Student
Room 202 (CFM-MIA Lab), Main Building-B area |
|
I am currently a Ph.D. student at the University of Electronic Science and Technology of China (UESTC), supervised by Prof. Xiaofeng Zhu.
Since 2023, I have been working online with RIKEN Center for Advanced Intelligence Project (RIKEN-AIP) and being mentored by Prof. Gang Niu.
I received my B.Eng. degree from UESTC in 2020, supervised by Prof. Yazhou Ren.
The research during my Ph.D. was multi-view/modal/graph and self-supervised deep clustering. In these areas, I have tried to provide novel insights to the community, and some major results are briefly highlighted below:
Interpretability of multi-view learning (ICCV'21, Inf.Fus.'23). First try to disentangle view-common and view-private information in generative models that can produce interpretable multi-view representations.
Data heterogeneity of multi-view learning (CVPR'22, NeurIPS'23). Propose to learn multi-level features to avoid objective conflicts, and a general and theory-driven self-weighting contrastive learning framework that is adaptive to heterogeneous multi-view data.
Data incompleteness of multi-view learning (AAAI'21, TIP'23). Propose an imputation-free deep framework for effectively handling incomplete multi-view data, and establish the connection between domain adaptation and multi-view by incorporating distribution discrepancy.
Algorithm robustness towards noisy views (TKDE'22, CVPR'24). First to theoretically investigate consistency / complementarity / noise robustness for multi-view learning, and suggest to consider the side effects of noisy views for algorithm designs in practical scenarios.
Single-&multi-view learning with robustness of noisy labels and noisy views
Incomplete and false correspondence in multimodal learning with domain adaption
Semi-supervised learning based on foundational pre-trained large models
My research has gained the attention of scholars in the same field and has been successfully applied by other scholars in practical application fields, such as multi-view/modal data analysis, medical data analysis, internet data analysis, etc. I summarized the source [code] and [paper] repositories hoping to promote academic research and applied research.
The research topics that I am currently working on include:
Investigating and Mitigating the Side Effects of Noisy Views in Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios
Jie Xu, Yazhou Ren, Xiaolong Wang, Lei Feng, Zheng Zhang, Gang Niu, Xiaofeng Zhu.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Self-Weighted Contrastive Learning among Multiple Views for Mitigating Representation Degeneration
Jie Xu, Shuo Chen, Yazhou Ren, Xiaoshuang Shi, Heng Tao Shen, Gang Niu, Xiaofeng Zhu.
Annual Conference on Neural Information Processing Systems (NeurIPS), 2023.
UNTIE: Clustering Analysis with Disentanglement in Multi-view Information Fusion
Jie Xu, Yazhou Ren, Xiaoshuang Shi, Heng Tao Shen, Xiaofeng Zhu.
Information Fusion (Inf.Fus.), 2023.
Adaptive Feature Projection with Distribution Alignment for Deep Incomplete Multi-view Clustering
Jie Xu, Chao Li, Liang Peng, Yazhou Ren, Xiaoshuang Shi, Heng Tao Shen, Xiaofeng Zhu.
IEEE Transactions on Image Processing (TIP), 2023.
Self-Supervised Discriminative Feature Learning for Deep Multi-View Clustering
Jie Xu, Yazhou Ren, Huayi Tang, Zhimeng Yang, Lili Pan, Yang Yang, Xiaorong Pu, Philip S. Yu, Lifang He.
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2023 (Highly cited paper).
Multi-Level Feature Learning for Contrastive Multi-View Clustering
Jie Xu†, Huayi Tang†, Yazhou Ren, Liang Peng, Xiaofeng Zhu, Lifang He.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 (Oral).
Deep Incomplete Multi-view Clustering via Mining Cluster Complementarity
Jie Xu, Chao Li, Yazhou Ren, Liang Peng, Yujie Mo, Xiaoshuang Shi, Xiaofeng Zhu.
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2022.
Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clustering
Jie Xu, Yazhou Ren, Huayi Tang, Xiaorong Pu, Xiaofeng Zhu, Ming Zeng, Lifang He.
IEEE/CVF International Conference on Computer Vision (ICCV), 2021.
Deep embedded multi-view clustering with collaborative training
Jie Xu, Yazhou Ren, Guofeng Li, Lili Pan, Ce Zhu, Zenglin Xu.
Information Sciences (Inf.Sci.), 2020.
A novel federated multi-view clustering method for unaligned and incomplete data fusion
Yazhou Ren, Xinyue Chen, Jie Xu, Jingyu Pu, Yonghao Huang, Xiaorong Pu, Ce Zhu, Xiaofeng Zhu, Zhifeng Hao, Lifang He.
Information Fusion (Inf.Fus.), 2024.
Federated Deep Multi-View Clustering with Global Self-Supervision
Xinyue Chen, Jie Xu, Yazhou Ren, Xiaorong Pu, Ce Zhu, Xiaofeng Zhu, Zhifeng Hao, Lifang He.
ACM International Conference on Multimedia (ACM MM), 2023.
Dual Label-Guided Graph Refinement for Multi-View Graph Clustering
Yawen Ling, Jianpeng Chen, Yazhou Ren, Xiaorong Pu, Jie Xu, Xiaofeng Zhu, Lifang He.
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023.
GATE: Graph CCA for Temporal SElf-supervised Learning for Label-efficient fMRI Analysis
Liang Peng, Nan Wang, Jie Xu, Xiaofeng Zhu, Xiaoxiao Li.
IEEE Transactions on Medical Imaging (TMI), 2022.
GRLC: Graph Representation Learning with Constraints
Liang Peng, Yujie Mo, Jie Xu, Jialie Shen, Xiaoshuang Shi, Xiaoxiao Li, Heng Tao Shen, Xiaofeng Zhu.
IEEE Transactions on Neural Networks and learning systems (TNNLS), 2022.
Simple unsupervised graph representation learning
Yujie Mo, Liang Peng, Jie Xu, Xiaoshuang Shi, Xiaofeng Zhu.
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2022 (Oral).
Dementia analysis from functional connectivity network with graph neural networks
Lujing Wang, Weifeng Yuan, Lu Zeng, Jie Xu, Yujie Mo, Xinxiang Zhao, Liang Peng.
Information Processing & Management (IP&M), 2022.
Role: Developing the key techniques of multi-source/-modal integration based on meta-learning.
Role: Developing multi-view/-modal representation learning and information fusion methods.
Role: Developing multi-view clustering algorithms based on deep representation learning.
Conference Reviewer
Journal Reviewer